dual processors and linux 1769

That is almost certainly the case. (However, my test case used Mandriva Linux 2006, not a Mac.) I recall being informed in either around 1987 and maybe around 1980 that Unix adjusted a process's priority each time slice that the process executed based on one or both of the following:

- If the process used all of its CPU time slice, its priority would be lowered slightly.

- If a process had to wait for I-O before using all of its CPU time slice, its priority would be increased slightly.

Independent of whether one, the other, or both mechanisms are used, the relative effect is basically the same. IIRC, the stated purpose of this is to help keep processes that do a significant amount of I-O from being starved for CPU time.

Being as OS-X uses a kernel based on Unix principles, and Linux is based on the same principles, I would guess both have such a mechanism.

However, even without a priority adjustment mechanism, a modern preemptive multiprocessing operating system will not lock up and become essentially unusable as had been claimed in the earlier posting to which I had responded.

-- Robert Riches (Yes, that is one of my email addresses.)